Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2048 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8413. Min Range: -8.8413
Max Act: 8.8413. Min Act: -0.1700
Data Index: 617692 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8413. Min Range: -8.8413
Max Act: 8.7163. Min Act: -0.1700
Data Index: 165801 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8413. Min Range: -8.8413
Max Act: 8.7163. Min Act: -0.1700
Data Index: 7204565 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8413. Min Range: -8.8413
Max Act: 8.7163. Min Act: -0.1700
Data Index: 31357 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8413. Min Range: -8.8413
Max Act: 8.6538. Min Act: -0.1700
Data Index: 6950213 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8413. Min Range: -8.8413
Max Act: 8.5913. Min Act: -0.1700
Data Index: 5567128 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8413. Min Range: -8.8413
Max Act: 8.5913. Min Act: -0.1700
Data Index: 5891335 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8413. Min Range: -8.8413
Max Act: 8.4663. Min Act: -0.1700
Data Index: 1611454 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8413. Min Range: -8.8413
Max Act: 8.4663. Min Act: -0.1700
Data Index: 5621812 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8413. Min Range: -8.8413
Max Act: 8.4663. Min Act: -0.1700
Data Index: 7789772 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8413. Min Range: -8.8413
Max Act: 8.4663. Min Act: -0.1700
Data Index: 7184028 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8413. Min Range: -8.8413
Max Act: 8.4663. Min Act: -0.1700
Data Index: 1194752 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8413. Min Range: -8.8413
Max Act: 8.4038. Min Act: -0.1700
Data Index: 883425 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8413. Min Range: -8.8413
Max Act: 8.4038. Min Act: -0.1700
Data Index: 6513413 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8413. Min Range: -8.8413
Max Act: 8.3413. Min Act: -0.1700
Data Index: 6466704 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8413. Min Range: -8.8413
Max Act: 8.3413. Min Act: -0.1700
Data Index: 7773381 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8413. Min Range: -8.8413
Max Act: 8.2788. Min Act: -0.1700
Data Index: 6487304 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8413. Min Range: -8.8413
Max Act: 8.3413. Min Act: -0.1700
Data Index: 5540284 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8413. Min Range: -8.8413
Max Act: 8.2788. Min Act: -0.1700
Data Index: 1069819 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8413. Min Range: -8.8413
Max Act: 8.2788. Min Act: -0.1700
Data Index: 2729705 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #19